Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    elements related to conditions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    held fixed, test data, training data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ніципалі
    -0.46
    ########.
    -0.40
    CAPIT
    -0.38
    UrlResolution
    -0.37
    通
    -0.37
    насе
    -0.36
    Хро
    -0.35
     Laut
    -0.35
     verla
    -0.35
    قلال
    -0.35
    POSITIVE LOGITS
    orianCalendar
    0.50
    usermodel
    0.45
     alternately
    0.45
    順番
    0.42
    localctx
    0.39
    GetEnumerator
    0.39
     focus
    0.39
    ErrorListener
    0.39
    ombres
    0.39
     kla
    0.38
    Act Density 0.170%

    No Known Activations